Skip to content

Add GCPVertexGeminiSFTConfig to python OptimizationConfig type #2962

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 7 commits into
base: main
Choose a base branch
from

Conversation

anndvision
Copy link
Contributor

@anndvision anndvision commented Jul 31, 2025

This PR adds the GCPVertexGeminiSFTConfig to OptimizationConfig in clients/python/tensorzero/__init__.py to make it visible to the python client when calling experimental_launch_optimization


Important

Add GCPVertexGeminiSFTConfig to Python client OptimizationConfig and update tests and Rust deserialization to support it.

  • Behavior:
    • Add GCPVertexGeminiSFTConfig to OptimizationConfig in __init__.py for visibility in Python client.
    • Update deserialize_optimization_config() in pyo3_helpers.rs to handle UninitializedGCPVertexGeminiSFTConfig.
  • Tests:
    • Add test_sync_gcp_vertex_gemini_sft() and test_async_gcp_vertex_gemini_sft() in test_optimization.py for synchronous and asynchronous testing of GCPVertexGeminiSFTConfig.
    • Modify mixed_rendered_samples in conftest.py to adjust tool parameters structure.

This description was created by Ellipsis for 193a3a8. You can customize this summary. It will automatically update as commits are pushed.

Copy link
Contributor

@Copilot Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull Request Overview

This PR adds support for GCP Vertex Gemini SFT (Supervised Fine-Tuning) configuration to the Python client's optimization configuration options. This expands the available optimization providers for the experimental_launch_optimization function.

  • Adds GCPVertexGeminiSFTConfig to the OptimizationConfig union type
  • Enables users to specify GCP Vertex Gemini as an optimization provider in Python

@GabrielBianconi GabrielBianconi added this pull request to the merge queue Aug 3, 2025
@github-merge-queue github-merge-queue bot removed this pull request from the merge queue due to failed status checks Aug 3, 2025
Copy link
Member

@GabrielBianconi GabrielBianconi left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Tests complained, I believe needs change in tensorzero-core/src/inference/types/pyo3_helpers.rs

@anndvision anndvision marked this pull request as draft August 5, 2025 19:15
@anndvision anndvision marked this pull request as ready for review August 11, 2025 12:04
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants